CN110442979A - The full Deformation Prediction method and system in the shield-tunneling construction tunnel based on BP neural network - Google Patents
The full Deformation Prediction method and system in the shield-tunneling construction tunnel based on BP neural network Download PDFInfo
- Publication number
- CN110442979A CN110442979A CN201910730664.6A CN201910730664A CN110442979A CN 110442979 A CN110442979 A CN 110442979A CN 201910730664 A CN201910730664 A CN 201910730664A CN 110442979 A CN110442979 A CN 110442979A
- Authority
- CN
- China
- Prior art keywords
- deformation prediction
- full deformation
- neural network
- candidate
- prediction index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010276 construction Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 49
- 238000012549 training Methods 0.000 claims abstract description 34
- 230000008569 process Effects 0.000 claims abstract description 29
- 238000012216 screening Methods 0.000 claims abstract description 7
- 238000004590 computer program Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 13
- 238000009826 distribution Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 239000011435 rock Substances 0.000 description 19
- 238000012544 monitoring process Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000006073 displacement reaction Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000009412 basement excavation Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000013139 quantization Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 239000002689 soil Substances 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000002002 slurry Substances 0.000 description 2
- 230000005641 tunneling Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000004925 denaturation Methods 0.000 description 1
- 230000036425 denaturation Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 238000007569 slipcasting Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D11/00—Lining tunnels, galleries or other underground cavities, e.g. large underground chambers; Linings therefor; Making such linings in situ, e.g. by assembling
- E21D11/04—Lining with building materials
- E21D11/08—Lining with building materials with preformed concrete slabs
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D9/00—Tunnels or galleries, with or without linings; Methods or apparatus for making thereof; Layout of tunnels or galleries
- E21D9/06—Making by using a driving shield, i.e. advanced by pushing means bearing against the already placed lining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mining & Mineral Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Structural Engineering (AREA)
- Health & Medical Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Architecture (AREA)
- Environmental & Geological Engineering (AREA)
- Civil Engineering (AREA)
- Lining And Supports For Tunnels (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Present disclose provides the full Deformation Prediction method and system in the shield-tunneling construction tunnel based on BP neural network.The full Deformation Prediction method, including obtain the candidate complete corresponding historical data of Deformation Prediction index and corresponding section of jurisdiction deflection；The subjective weight of candidate full Deformation Prediction index is calculated using analytic hierarchy process (AHP), the objective weight that candidate full Deformation Prediction index is calculated using rough set theory calculates the combining weights of candidate full Deformation Prediction index according to the difference degree of subjective weight and objective weight；Screening is greater than or equal to the full Deformation Prediction index of candidate corresponding to the combining weights of preset threshold as full Deformation Prediction index；Using the corresponding historical data of each full Deformation Prediction index and the corresponding combination multiplied by weight, the training sample data of BP neural network, training BP neural network are obtained；It obtains the corresponding real time data of full Deformation Prediction index, the real time data that will acquire and is input to after the corresponding combination multiplied by weight in the BP neural network of training completion, export section of jurisdiction deflection.
Description
Technical field
The disclosure belongs to the full Deformation Prediction field in tunnel more particularly to a kind of shield-tunneling construction tunnel based on BP neural network
Full Deformation Prediction method and system.
Background technique
Only there is provided background technical informations relevant to the disclosure for the statement of this part, it is not necessary to so constitute first skill
Art.
Submerged tunnel engineering due to its with the stronger war of resistance strive damage capability and by Effect of Natural Disaster it is small etc. it is excellent
Gesture；Shipping is not destroyed, does not influence the own characteristics such as marine ecosystem environment, is widely applied in wearing Hai Yuejiang engineering.Shield method is applied
Work is current state-of-the-art tunnel construction technology, since its speed of application is fast, the advantages that high safety, environmental perturbation is small, and one
The directly main construction method as submerged tunnel.But due to the complicated special construction environment of submerged tunnel, shield construction is still deposited
In security risk.
It is identical as conventional tunnel construction, in Analysis on Shield Tunnel Driven Process, be equally faced with tunnel support structure deform it is excessive
Problem.For shield construction tunnel, tunnel segment structure is the main supporting construction in tunnel.And the displacement of section of jurisdiction is excessive not only
It will cause the faulting of slab ends between section of jurisdiction, cause connection bolt to be cut and even cut, cause structural failure；Segment deformation is excessive simultaneously can also
The bolt of caused connection section of jurisdiction destroys, to cause the destruction of structurally waterproof layer, causes tunnel the quality such as percolating water occur and asks
Topic；In the construction process, due to self gravity and the collective effect of duct piece float upward power, there may be offices for upper earthing for submerged tunnel
Portion compression, crack and form through crack, cause certain impervious stratums become pervious bed, while upper earthing by buoyancy make
With causing the further deformation of tunnel duct piece.If failing to find segment deformation abnormal problem in time, section of jurisdiction country rock eccentric force is produced
Raw additional bending moment may cause section of jurisdiction crack even rhegma when serious.Therefore adequate measures is taken to control duct pieces of shield tunnel
Displacement not only may insure that tunnel line style meets design requirement, and guarantee the emphasis of clearance of tunnel and construction quality.In
During tunnel excavation and support system apply, monitoring measurement is the important of country rock dynamic changing process in grasp constructing tunnel
Means, the data of monitoring measurement can directly show the dynamic change and support conditions of a certain period in tunnel.And it can be with
Carrying-deformation-time response of country rock and supporting construction is determined by monitoring measurement.
Problem on deformation in conventional tunnel work progress be it is unavoidable, shield construction tunnel is also such.Due to
The limitation in shield machine interior construction section, can not placement sensor element and monitoring measurement in a distance of excavation face rear
Monitoring point.Inventors have found that all Multi sectionals of tunnel internal can not obtain the deformation information in tunnel in time, so as to will lead to certain
Section segment deformation is excessive and cannot be monitored in time.For submerged tunnel shield construction, segment deformation
The excessive direct indirect loss that may cause and consequence are even more inestimable.
Summary of the invention
To solve the above-mentioned problems, the first aspect of the disclosure provides a kind of shield-tunneling construction tunnel based on BP neural network
The full Deformation Prediction method in road the reason of considering experience and recognize aspect, calculates candidate change entirely using analytic hierarchy process (AHP)
The subjective weight of shape prediction index calculates the objective weight of candidate full Deformation Prediction index using rough set theory, and according to master
The difference degree of weight and objective weight is seen to calculate the combining weights of candidate full Deformation Prediction index, then pre- to candidate full deformation
It surveys index and carries out reduction, determine input node of the full Deformation Prediction index as BP neural network model, export section of jurisdiction deflection,
Improve the accuracy of the full Transfiguration Prediction Result in shield-tunneling construction tunnel.
To achieve the goals above, the disclosure adopts the following technical scheme that
A kind of full Deformation Prediction method in the shield-tunneling construction tunnel based on BP neural network, comprising:
Obtain the candidate complete corresponding historical data of Deformation Prediction index and corresponding section of jurisdiction deflection；
The subjective weight that candidate full Deformation Prediction index is calculated using analytic hierarchy process (AHP), is calculated candidate using rough set theory
The objective weight of full Deformation Prediction index, and candidate full deformation is calculated in advance according to the difference degree of subjective weight and objective weight
Survey the combining weights of index；
Screening is greater than or equal to the full Deformation Prediction index of candidate corresponding to the combining weights of preset threshold as full deformation
Prediction index；
Using the corresponding historical data of each full Deformation Prediction index and the corresponding combination multiplied by weight, BP neural network is obtained
Training sample data, and then construct training sample set and training BP neural network；
The corresponding real time data of full Deformation Prediction index is obtained, after the real time data that will acquire and the corresponding combination multiplied by weight
It is input in the BP neural network of training completion, exports section of jurisdiction deflection.
The second aspect of the disclosure provides a kind of full Deformation Prediction system in shield-tunneling construction tunnel based on BP neural network
System.
A kind of full Deformation Prediction system in the shield-tunneling construction tunnel based on BP neural network, comprising:
Candidate full Deformation Prediction achievement data obtains module, is used to obtain the corresponding history of candidate full Deformation Prediction index
Data and corresponding section of jurisdiction deflection；
Combining weights computing module is used to calculate the subjective power of candidate full Deformation Prediction index using analytic hierarchy process (AHP)
Weight, calculates the objective weight of candidate full Deformation Prediction index using rough set theory, and according to subjective weight and objective weight
Difference degree calculates the combining weights of candidate full Deformation Prediction index；
Full Deformation Prediction index screening module is used to screen corresponding to the combining weights for being greater than or equal to preset threshold
Candidate full Deformation Prediction index is as full Deformation Prediction index；
BP neural network training module is used to utilize the corresponding historical data of each full Deformation Prediction index and respective sets
Multiplied by weight is closed, the training sample data of BP neural network are obtained, and then constructs training sample set and training BP neural network；
Segment deformation amount prediction module is used to obtain the corresponding real time data of full Deformation Prediction index, the reality that will acquire
When data and the corresponding combination multiplied by weight after be input to training completion BP neural network in, export section of jurisdiction deflection.
A kind of computer readable storage medium is provided in terms of the third of the disclosure.
A kind of computer readable storage medium, is stored thereon with computer program, realization when which is executed by processor
Step in the full Deformation Prediction method in the shield-tunneling construction tunnel based on BP neural network as described above.
4th aspect of the disclosure provides a kind of terminal.
A kind of terminal can be run on a memory and on a processor including memory, processor and storage
Computer program, the processor realize the shield-tunneling construction tunnel as described above based on BP neural network when executing described program
Step in the full Deformation Prediction method in road.
The beneficial effect of the disclosure is:
The present disclosure contemplates that the reason of experience and cognition aspect, calculate candidate full Deformation Prediction using analytic hierarchy process (AHP) and refer to
Target subjectivity weight, calculates the objective weight of candidate full Deformation Prediction index using rough set theory, and according to subjective weight and
The difference degree of objective weight calculates the combining weights of candidate full Deformation Prediction index, then to candidate full Deformation Prediction index into
Row reduction determines input node of the full Deformation Prediction index as BP neural network model, exports section of jurisdiction deflection, improves shield
The accuracy of the full Transfiguration Prediction Result of structure construction tunnel.
Detailed description of the invention
The Figure of description for constituting a part of this disclosure is used to provide further understanding of the disclosure, and the disclosure is shown
Meaning property embodiment and its explanation do not constitute the improper restriction to the disclosure for explaining the disclosure.
Fig. 1 is the full Deformation Prediction method stream in the shield-tunneling construction tunnel based on BP neural network that the embodiment of the present disclosure provides
Cheng Tu.
Fig. 2 is the segment deformation parameter schematic diagram that the embodiment of the present disclosure provides.
Fig. 3 is the full deformation curve of tense that the embodiment of the present disclosure provides.
Fig. 4 is the full Deformation Prediction system knot in the shield-tunneling construction tunnel based on BP neural network that the embodiment of the present disclosure provides
Structure schematic diagram.
Specific embodiment
The disclosure is described further with embodiment with reference to the accompanying drawing.
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the disclosure.Unless another
It indicates, all technical and scientific terms used herein has usual with disclosure person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the disclosure.As used herein, unless the context clearly indicates otherwise, otherwise singular
Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
Embodiment 1
Present embodiments provide a kind of full Deformation Prediction method in shield-tunneling construction tunnel based on BP neural network, such as Fig. 1
It is shown, it specifically includes:
S101: the candidate complete corresponding historical data of Deformation Prediction index and corresponding section of jurisdiction deflection are obtained.
Deformation monitoring during constructing tunnel is the important evidence of security control and construction guidance in work progress, and engineering is applied
By being monitored measurement using total station to laying monitoring point is carried out in tunnel during work, by being carried out to initial data
Processing, obtains final tunnel deformation data.The content that project monitor and control measures is mainly the deformation monitoring of Structural Test of Tunnel Segments, including
Section of jurisdiction vertical displacement monitoring and horizontal displacement monitoring.
Similarly with traditional New Austrian Tunneling Method construction, as the main support form in entire tunnel, mistake of the section of jurisdiction in laying
The support system of a relative securement is constituted in journey, to guarantee the stabilization in tunnel in work progress.Analysis on Shield Tunnel Driven Process
In, the propulsion of shield machine and the laying of section of jurisdiction can generate inevitably disturbance to the country rock of surrounding and the soil body.Make section of jurisdiction
For the main supporting construction in tunnel, vertical deformation and horizontal change can be generated under the uneven perturbation action of country rock or the soil body
Shape, as shown in Figure 2.
Deform that there are certain range of disturbance, shield-tunneling construction mistakes it is found that shield-tunneling construction process is to shoulder effect entirely by tense
Cheng Zhong, tunnel support structure-tunnel segment structure in a distance of excavation face rear still will receive construction infection, but different stagnant
The segment deformation degree of distance is different afterwards.As shown in Figure 3 in the construction process by shield machine, the ζ of same period1,ζ2,ζ3...
ζnThe tense of the referred to as period deforms entirely.
In specific implementation, the candidate full Deformation Prediction index, including but not limited to edpth of tunnel, cover across than, it is natural
Density, elasticity modulus, Poisson's ratio, driving speed and delay distance.
(1) edpth of tunnel
For submerged tunnel, powerful Water And Earth Pressures are the major influence factors of constructing tunnel process stability, also
It is the important factor in order of segment deformation.Edpth of tunnel is deeper, and it is bigger to cover water and soil load thereon, is needed by construction disturbance deformation steady
The fixed time is also longer.The present embodiment is using the edpth of tunnel, that is, tunnel and country rock contact upper surface to sea level in actual condition
Distance (non-sea area section is to surface distance) is as candidate full Deformation Prediction index.
(2) it covers across than e
For tunneling boring constructing tunnel, cross dimensions is bigger, and work progress is influenced caused by Tunnel Stability may be just
It is bigger.It covers across the ratio than i.e. tunnel above rock thickness degree and tunnel diameter.It covers across than increasing, tunnel excavation is in the process to tunnel
Surrounding water disturbance in road increases.In shield-tunneling construction tunnel, the ratio between tunnel superincumbent stratum thickness and tunnel diameter are referred to.
(3) natural density ρ
The degree of stability for determining rock mass to a certain extent of the natural density of rock mass, shaping age, class with rock mass
Type and intensity have certain relationship, affect the stability of the country rock of submerged tunnel to a certain extent.
(4) elastic modulus E
Elasticity modulus is the important indicator for influencing stability of rock-soil body, and size embodies the deformation behaviour of rock mass.According to
The existing elasticity modulus criteria for classifying divides the corresponding elasticity modulus of different distortion grade.
(5) Poisson's ratio μ
Poisson's ratio is a kind of deformation state parameter changed with stress state and loading mode, the size of Poisson's ratio value
Largely influence the horizontal distribution of stress.Poisson's ratio is the important parameter of deformational characteristics of rock bodies, is had to rock mass deformation
Significant impact.
(6) driving speed V
Slurry balance shield construction, the driving speed under the conditions of normal construction tunnels are generally 20~50mm/min.At present
Known slurry shield driving speed is most 92mm/min fastly.On the one hand the driving speed of shield machine is demonstrated by constructing tunnel process and encloses
The superiority and inferiority of rock, while also can be to the disturbance of country rock, it is believed that driving speed is faster, relatively higher to country rock level of disruption, because
Practice of construction speed is carried out quantization modulation by this.It is shown in Table 1:
1 shield-tunneling construction of table tunnels state
(7) delay distance R
It is larger to the disturbance of country rock around during shield-tunneling construction, after the completion of first bushing pipe piece laying and slip casting, country rock disturbance
And segment deformation is being controlled to a certain degree.Shield-tunneling construction to segment deformation influence can with the increase of delay distance and
Weaken, is obvious, therefore distance can be will be late by and regard section of jurisdiction as by the evaluation and prediction for being influenced to be deformed of constructing
Index.As shown, wherein R is construction delay distance, the segment deformation after this section of distance is considered as hysteresis set.According to work
Journey project reality carries out discretization in the section 0~150m to delay distance R.
In view of practice of construction process can not completely effectively be monitored full deformation data, therefore full deformation data
Obtain the method using numerical simulation or model experiment.Preferential uses method for numerical simulation.Obtain initial sample data set
Close N.By the full deformation curve of process it is found that during constructing tunnel, segment deformation can undergo three stages deformed above, according to when
The full deformation curve of state carries out regression analysis, is drawn up a contract according to the initial sample data sets N that numerical simulation or model experiment obtain
When compared according to the data of actual measurement and be adjusted the out of phase of two curvilinear equations, after obtaining data correction
Sample data set N '.As the data sample for full Deformation Prediction research.
Shield tunnel construction deflection is innovatively subjected to quantization modulation on the basis of tunnel deformation research at this stage, is considered
To shield-tunneling construction segment deformation requirement, respectively to section of jurisdiction vertical displacement in 0~60mm quantization modulation, section of jurisdiction horizontal convergence is 0
~40mm quantization modulation.
2 segment deformation hierarchical level of table divides
Segment deformation is divided into 5 grades, class set S={ the full distortion level in submerged tunnel section of jurisdiction of shield construction }
={ S1,S2,S3,S4,S5Establish hierarchic space and determine each evaluation index in the section of each grade quantizing.And provide S1=
{ having no obvious deformation }；S2={ deformation is smaller }；S3={ having obvious deformation }；S4={ denaturation is larger }；S5={ deformation is very big }；It is right
Grade is answered to carry out stability description such as table 2.
S102: the subjective weight of candidate full Deformation Prediction index is calculated using analytic hierarchy process (AHP), using rough set theory meter
The objective weight of candidate full Deformation Prediction index is calculated, and candidate is calculated entirely according to the difference degree of subjective weight and objective weight
The combining weights of Deformation Prediction index.
In specific implementation, with analytic hierarchy process (AHP) compared in pairs by evaluation index, expert is used for reference by policymaker and is learned
The standard that the suggestion of person is evaluated using 1~9 scale as index importance carries out importance global weight to index, and construction is sentenced
Disconnected matrix Gn×n(wherein IijIndicate that i index significance level compared with j index is Iij):
Evaluation index is to the influence degree of the result of decision using 1~9 scale as the quantitative expression of index significance level.Such as
IijIt indicates i index and j Indexes Comparison significance level is Iij, same i index is compared with j index, importance degree 1/
Iij.Using algorithm based on the largest eigenvalue judgment matrix Gn×nAcquire maximum eigenvalue λmaxAnd corresponding feature vector α, by formula (1)~
(3) it is calculated, obtains the importance ranking of evaluation index.
G α=λmaxα (1)
Finally to avoid due in decision process, excessive index and sequence contradiction is generated in importance comparison process,
Consistency ratio index CR is introduced, and is defined:
CR=CI/RI (2)
Wherein coincident indicator CI and average homogeneity index RI calculation formula such as formula (4).
CI=(λmax-n)/(n-1) (3)
Wherein coincident indicator RI value is according to table 3:
3 RI value of table
Judgment matrix is defined based on consistency discrimination coefficient, as CR < 0.1, then it is assumed that judgment matrix has acceptable
Consistency, the weight w of Deformation Prediction indexiIt can be determined by the corresponding feature vector of maximum eigenvalue:
Wherein 0≤wi≤ 1, andαiFor corresponding i-th of the element of weight vectors.
And think as CR < 0.1, judgment matrix G has acceptable consistency, obtains what analytic hierarchy process (AHP) calculated at this time
Weighted value wi(w1,w2,w3......wn).It is on the contrary, it is believed that the degree that judgment matrix G deviates consistency is excessive, needs to the member in G
Plain value is modified.
Objective computation method is calculated using rough set calculation method.It is preferentially complete according to submerged tunnel shield construction
Deformation Prediction system.Decision table is established, the objective weight of each evaluation index is calculated using rough set calculation method.Using rough set
Theory obtains the objective weight value of prediction index.It is specific to calculate shown in steps are as follows:
If S=(U, R) is a knowledge-representation system, wherein U is known as domain, indicates the nonempty finite set of object；R table
Show conditional attribute collection.Wherein P, Q belong to R, if R=P ∪ Q is simultaneouslyC=(U, R, P, Q) is then used as decision
Table.
Support S of the P to Qp(Q) it can be calculated by formula:
SP(Q)=| posp(Q)|/|U|(0≤γP(Q)≤1) (5)
posp(Q) P is expressed as to the normal state region of Q.γp(Q) then indicate that Q depends on the degree of P.In conditional attribute set
Remove index PiExcept, support γ of remaining index for Qp-pi(Q) it can be calculated by formula:
For belonging to the subset P of PiTo the different degree σ of QPQ(Pi) be represented by
PiWeight eiIt can indicate are as follows:
Objective weight set e is obtained by rough seti(e1,e2,e3......en)。
To guarantee the difference degree between weighted value that two methods obtain and the difference degree phase of corresponding distribution coefficient
Unanimously, deviation function method f (x) is introduced, indicates the difference degree of each index weights, calculate two kinds of power using formula (9)~(13)
The distribution coefficient α, β of weight.
If combining weights are Wi, combined weights weight values are the two linear weighted function:
Wi=α wi+βei (10)
α and β are respectively the distribution coefficient of two kinds of weights in formula, for make between different weights difference degree and distribution coefficient it
Between difference degree it is consistent, enable two formulas equal, and the condition that uses restraint:
Alpha+beta=1 (11)
In order to keep subjective and objective weight difference degree consistent with distribution coefficient difference degree, distance function should be made to meet:
f(wi,ei)=(alpha-beta)2 (12)
In conclusion Simultaneous Equations, enable:
The weight that two kinds of calculation methods obtain is obtained by joint type (9)~(11).Distribution coefficient obtained is substituted into
Equation group (13), can be obtained final weight Wi.By analyzing final weight, final full Deformation Prediction index is obtained
And its weight Wi(W1,W2,W3......Wn).N indicates the quantity of candidate full Deformation Prediction index.
S103: screening is greater than or equal to the full Deformation Prediction index of candidate corresponding to the combining weights of preset threshold as complete
Deformation Prediction index；
For weight calculation as a result, by weight be less than preset threshold (such as: 0.1), if it exists it is more then by weight minimum
Calculated result carry out reduction, obtain reduction after prediction index set Gi(G1,G2,G3......Gs), wherein (s≤n).
S104: the corresponding historical data of each full Deformation Prediction index and the corresponding combination multiplied by weight are utilized, BP mind is obtained
Training sample data through network, and then construct training sample set and training BP neural network.
For the influence for avoiding the unit dimension due to different prediction index from may cause prediction result, input is joined
Number is normalized, and is normalized according to following formula.
Wherein gijFor j-th of data of i-th of index, max (gi) be i-th of index maximum value, min (gi) it is i-th
The minimum value of index.bijFor the result after j-th of data normalization of i-th of index.
Parameter is attributed to [0,1] section, using the data sample after normalization as progress input data.
Rule of thumb formula determines the structure of neural network:
Wherein h is hidden layer neuron number, and i is input layer number, and o is output layer neuron number.
Selectively appropriate training function is trained.This position is first layer transmission function, is defaulted as tansig.The
Two layers of transmission function, preferential selection are traingdx.Band momentum gradient decline modified training function learngdm.
According to the scale for requiring and calculating data is calculated, the precision of model training, the learning error of training process are set
And train epochs.
Training is completed, and model is established, and the calculating for analysis project example obtains prediction result y.Prediction result y is carried out
Renormalization obtains final prediction result Y.By the way that prediction result analysis is verified prediction model and is subject to perfect.
Y=y* (ymax-ymin)+ymin (17)
S105: the corresponding real time data of full Deformation Prediction index, the real time data that will acquire and the corresponding combination weight are obtained
It is input to after multiplication in the BP neural network of training completion, exports section of jurisdiction deflection.
In another embodiment, this method further include:
According to the division of the default corresponding distortion level of segment deformation amount, corresponding deformation of segment deformation amount etc. is obtained
Grade.
Embodiment 2
As shown in figure 4, a kind of full Deformation Prediction system in shield-tunneling construction tunnel based on BP neural network of the present embodiment,
Include:
(1) candidate full Deformation Prediction achievement data obtains module, and it is corresponding to be used to obtain candidate full Deformation Prediction index
Historical data and corresponding section of jurisdiction deflection；
It is obtained in module in the candidate full Deformation Prediction achievement data, the candidate full Deformation Prediction index, including but
Be not limited to edpth of tunnel, cover across than, natural density, elasticity modulus, Poisson's ratio, driving speed and delay distance.
(2) combining weights computing module is used to calculate the subjectivity of candidate full Deformation Prediction index using analytic hierarchy process (AHP)
Weight calculates the objective weight of candidate full Deformation Prediction index using rough set theory, and according to subjective weight and objective weight
Difference degree calculate the combining weights of candidate full Deformation Prediction index；
In the combining weights computing module, the combining weights of candidate full Deformation Prediction index are as follows:
Wi=α wi+βei
Wherein, WiFor combining weights；f(wi,ei) indicate distance function, refer to subjective weight wiWith objective weight eiDifference
Off course degree；α, β respectively indicate subjective weight wiWith objective weight eiDistribution coefficient；N indicates the number of candidate full Deformation Prediction index
Amount.
(3) full Deformation Prediction index screening module, it is right more than or equal to the combining weights of preset threshold institute to be used to screen
The full Deformation Prediction index of the candidate answered is as full Deformation Prediction index；
(4) BP neural network training module is used to utilize the corresponding historical data of each full Deformation Prediction index and phase
It answers combining weights to be multiplied, obtains the training sample data of BP neural network, and then construct training sample set and training BP nerve
Network；
(5) segment deformation amount prediction module is used to obtain the corresponding real time data of full Deformation Prediction index, will acquire
It is input to after real time data and the corresponding combination multiplied by weight in the BP neural network of training completion, exports section of jurisdiction deflection.
In another embodiment, the system, further includes:
Distortion level output module is used to be obtained according to the division for presetting the corresponding distortion level of segment deformation amount
The corresponding distortion level of segment deformation amount.
Embodiment 3
The present embodiment provides a kind of computer readable storage mediums, are stored thereon with computer program, and the program is processed
The step in the full Deformation Prediction method in the shield-tunneling construction tunnel based on BP neural network as shown in Figure 1 is realized when device executes.
Embodiment 4
The present embodiment provides a kind of terminal, including memory, processor and storage on a memory and can located
The computer program that runs on reason device, the processor are realized as shown in Figure 1 based on BP neural network when executing described program
Shield-tunneling construction tunnel full Deformation Prediction method in step.
It should be understood by those skilled in the art that, embodiment of the disclosure can provide as method, system or computer program
Product.Therefore, the shape of hardware embodiment, software implementation or embodiment combining software and hardware aspects can be used in the disclosure
Formula.Moreover, the disclosure, which can be used, can use storage in the computer that one or more wherein includes computer usable program code
The form for the computer program product implemented on medium (including but not limited to magnetic disk storage and optical memory etc.).
The disclosure is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present disclosure
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random
AccessMemory, RAM) etc..
The foregoing is merely preferred embodiment of the present disclosure, are not limited to the disclosure, for the skill of this field
For art personnel, the disclosure can have various modifications and variations.It is all within the spirit and principle of the disclosure, it is made any to repair
Change, equivalent replacement, improvement etc., should be included within the protection scope of the disclosure.
Claims (10)
1. a kind of full Deformation Prediction method in the shield-tunneling construction tunnel based on BP neural network characterized by comprising
Obtain the candidate complete corresponding historical data of Deformation Prediction index and corresponding section of jurisdiction deflection；
The subjective weight that candidate full Deformation Prediction index is calculated using analytic hierarchy process (AHP) is become using rough set theory calculating candidate is complete
The objective weight of shape prediction index, and candidate full Deformation Prediction is calculated according to the difference degree of subjective weight and objective weight and is referred to
Target combining weights；
Screening is greater than or equal to the full Deformation Prediction index of candidate corresponding to the combining weights of preset threshold as full Deformation Prediction
Index；
Using the corresponding historical data of each full Deformation Prediction index and the corresponding combination multiplied by weight, the instruction of BP neural network is obtained
Practice sample data, and then constructs training sample set and training BP neural network；
It obtains the corresponding real time data of full Deformation Prediction index, the real time data that will acquire and is inputted after the corresponding combination multiplied by weight
In the BP neural network completed to training, section of jurisdiction deflection is exported.
2. the full Deformation Prediction method in the shield-tunneling construction tunnel based on BP neural network, feature exist as described in claim 1
In this method further include:
According to the division of the default corresponding distortion level of segment deformation amount, the corresponding distortion level of segment deformation amount is obtained.
3. the full Deformation Prediction method in the shield-tunneling construction tunnel based on BP neural network, feature exist as described in claim 1
In, the candidate full Deformation Prediction index, including edpth of tunnel, cover across than, natural density, elasticity modulus, Poisson's ratio, driving speed
Degree and delay distance.
4. the full Deformation Prediction method in the shield-tunneling construction tunnel based on BP neural network, feature exist as described in claim 1
In the combining weights of candidate full Deformation Prediction index are as follows:
Wi=α wi+βei
Wherein, WiFor combining weights；f(wi,ei) indicate distance function, refer to subjective weight wiWith objective weight eiDifference journey
Degree；α, β respectively indicate subjective weight wiWith objective weight eiDistribution coefficient；N indicates the quantity of candidate full Deformation Prediction index.
5. a kind of full Deformation Prediction system in the shield-tunneling construction tunnel based on BP neural network characterized by comprising
Candidate full Deformation Prediction achievement data obtains module, is used to obtain the corresponding historical data of candidate full Deformation Prediction index
And corresponding section of jurisdiction deflection；
Combining weights computing module is used to be calculated the subjective weight of candidate full Deformation Prediction index using analytic hierarchy process (AHP), adopted
The objective weight of candidate full Deformation Prediction index is calculated with rough set theory, and according to the difference journey of subjective weight and objective weight
It spends to calculate the combining weights of candidate full Deformation Prediction index；
Full Deformation Prediction index screening module is used to screen candidate corresponding to the combining weights for being greater than or equal to preset threshold
Full Deformation Prediction index is as full Deformation Prediction index；
BP neural network training module is used to that the corresponding historical data of each full Deformation Prediction index and the corresponding combination to be utilized to weigh
Heavy phase multiplies, and obtains the training sample data of BP neural network, and then constructs training sample set and training BP neural network；
Segment deformation amount prediction module is used to obtain the corresponding real time data of full Deformation Prediction index, the real-time number that will acquire
According to be input to after the corresponding combination multiplied by weight training completion BP neural network in, export section of jurisdiction deflection.
6. the full Deformation Prediction system in the shield-tunneling construction tunnel based on BP neural network, feature exist as claimed in claim 5
In the system, further includes:
Distortion level output module is used to obtain section of jurisdiction according to the division for presetting the corresponding distortion level of segment deformation amount
The corresponding distortion level of deflection.
7. the full Deformation Prediction system in the shield-tunneling construction tunnel based on BP neural network, feature exist as claimed in claim 5
In in the candidate full Deformation Prediction achievement data acquisition module, the candidate full Deformation Prediction index, including tunnel are buried
It is deep, cover across than, natural density, elasticity modulus, Poisson's ratio, driving speed and delay distance.
8. the full Deformation Prediction system in the shield-tunneling construction tunnel based on BP neural network, feature exist as claimed in claim 5
In, in the combining weights computing module, the combining weights of candidate full Deformation Prediction index are as follows:
Wi=α wi+βei
Wherein, WiFor combining weights；f(wi,ei) indicate distance function, refer to subjective weight wiWith objective weight eiDifference journey
Degree；α, β respectively indicate subjective weight wiWith objective weight eiDistribution coefficient；N indicates the quantity of candidate full Deformation Prediction index.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The full Deformation Prediction side such as the shield-tunneling construction tunnel of any of claims 1-4 based on BP neural network is realized when row
Step in method.
10. a kind of terminal including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes such as base of any of claims 1-4 when executing described program
Step in the full Deformation Prediction method in the shield-tunneling construction tunnel of BP neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910730664.6A CN110442979B (en) | 2019-08-08 | 2019-08-08 | BP neural network-based shield construction tunnel total deformation prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910730664.6A CN110442979B (en) | 2019-08-08 | 2019-08-08 | BP neural network-based shield construction tunnel total deformation prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110442979A true CN110442979A (en) | 2019-11-12 |
| CN110442979B CN110442979B (en) | 2021-04-13 |
Family
ID=68434031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910730664.6A Active CN110442979B (en) | 2019-08-08 | 2019-08-08 | BP neural network-based shield construction tunnel total deformation prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110442979B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112146748A (en) * | 2020-09-03 | 2020-12-29 | 深圳大学 | Method for positioning vibration source around tunnel by combining tunnel and earth surface monitoring data |
| CN112762853A (en) * | 2020-12-28 | 2021-05-07 | 中国科学院武汉岩土力学研究所 | Method and equipment for monitoring full deformation of duct piece in tunnel shield process |
| CN113240095A (en) * | 2021-06-07 | 2021-08-10 | 北京理工大学 | Casting cylinder cover mechanical property prediction method based on rough set and neural network |
| CN113743440A (en) * | 2021-01-13 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Information processing method and device and storage medium |
| CN114254562A (en) * | 2021-12-20 | 2022-03-29 | 浙江大学 | Neural network-based shield tunnel segment floating prediction method |
| CN115217152A (en) * | 2022-07-29 | 2022-10-21 | 招商局重庆交通科研设计院有限公司 | Method and device for predicting opening and closing deformation of immersed tunnel pipe joint |
| CN117235874A (en) * | 2023-11-14 | 2023-12-15 | 中电建铁路建设投资集团有限公司 | Track deformation prediction method and system based on shield tunneling |
| CN117474170A (en) * | 2023-11-17 | 2024-01-30 | 中电建铁路建设投资集团有限公司 | Shield settlement deformation model construction method based on neural network |
| CN117988867A (en) * | 2024-02-01 | 2024-05-07 | 中交隧道工程局有限公司 | Shield segment floating prediction method considering forming sequence influence |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU1740301A (en) * | 1999-11-11 | 2001-06-06 | Ballast Nedam Infra B.V. | Device and method for drilling in a subsurface |
| US20070192045A1 (en) * | 2003-07-09 | 2007-08-16 | Peter Brett | System and method for sensing and interpreting dynamic forces |
| CN101344389A (en) * | 2008-08-20 | 2009-01-14 | 中国建筑第八工程局有限公司 | Method for estimating tunnel surrounding rock displacement by neural network |
| US7508701B1 (en) * | 2006-11-29 | 2009-03-24 | The Board Of Trustees Of The Leland Stanford Junior University | Negative differential resistance devices and approaches therefor |
| CN103093400A (en) * | 2013-01-24 | 2013-05-08 | 华中科技大学 | Adjacent building safety quantitative evaluation method in tunnel construction |
| CN104766129A (en) * | 2014-12-31 | 2015-07-08 | 华中科技大学 | Subway shield construction surface deformation warning method based on temporal and spatial information fusion |
| EP3080395A2 (en) * | 2013-12-13 | 2016-10-19 | SWS Engineering S.p.A. | Procedure for the construction of cross passages in double pipe tunnels |
| CN106547986A (en) * | 2016-11-08 | 2017-03-29 | 苏州大学 | A kind of tunnel soil pressure load computational methods |
| CN107092990A (en) * | 2017-05-03 | 2017-08-25 | 西安电子科技大学 | The shield construction ground settlement forecast system and method analyzed based on big data |
-
2019
- 2019-08-08 CN CN201910730664.6A patent/CN110442979B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU1740301A (en) * | 1999-11-11 | 2001-06-06 | Ballast Nedam Infra B.V. | Device and method for drilling in a subsurface |
| US20070192045A1 (en) * | 2003-07-09 | 2007-08-16 | Peter Brett | System and method for sensing and interpreting dynamic forces |
| US7508701B1 (en) * | 2006-11-29 | 2009-03-24 | The Board Of Trustees Of The Leland Stanford Junior University | Negative differential resistance devices and approaches therefor |
| CN101344389A (en) * | 2008-08-20 | 2009-01-14 | 中国建筑第八工程局有限公司 | Method for estimating tunnel surrounding rock displacement by neural network |
| CN103093400A (en) * | 2013-01-24 | 2013-05-08 | 华中科技大学 | Adjacent building safety quantitative evaluation method in tunnel construction |
| EP3080395A2 (en) * | 2013-12-13 | 2016-10-19 | SWS Engineering S.p.A. | Procedure for the construction of cross passages in double pipe tunnels |
| CN104766129A (en) * | 2014-12-31 | 2015-07-08 | 华中科技大学 | Subway shield construction surface deformation warning method based on temporal and spatial information fusion |
| CN106547986A (en) * | 2016-11-08 | 2017-03-29 | 苏州大学 | A kind of tunnel soil pressure load computational methods |
| CN107092990A (en) * | 2017-05-03 | 2017-08-25 | 西安电子科技大学 | The shield construction ground settlement forecast system and method analyzed based on big data |
Non-Patent Citations (7)
| Title |
|---|
| BINGHUAZHOU ET AL: "Longitudinaljetventilationcalculationandapplicationoflonghighwaytunnel", 《JOURNAL OF ENGINEERING DESIGN AND TECHNOLOGY 》 * |
| LI JIAN ET AL: "Analysis of deformation regularity of soil in large section shallow loess tunnel", 《2010 INTERNATIONAL CONFERENCE ON MECHANIC AUTOMATION AND CONTROL ENGINEERING》 * |
| YIGUO XUE ET AL: "A prediction model for overlying rock thickness of subsea tunnel: A hybrid intelligent system", 《MARINE GEORESOURCES & GEOTECHNOLOGY》 * |
| 吴瑞: "盾构下穿施工对既有立交桥桩基的影响分析", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 周振民 等: "基于PSR－改进模糊集对分析模型的河流健康评价", 《中国农村水利水电》 * |
| 周纯择 等: "南昌上软下硬地层中盾构施工地表沉降的BP神经网络预测方法", 《防灾减灾工程学报》 * |
| 杨欢欢 等: "地铁盾构施工地表变形的神经网络预测及应用", 《中国科技论文》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112146748B (en) * | 2020-09-03 | 2022-12-23 | 深圳大学 | Method for positioning vibration source around tunnel by combining tunnel and earth surface monitoring data |
| CN112146748A (en) * | 2020-09-03 | 2020-12-29 | 深圳大学 | Method for positioning vibration source around tunnel by combining tunnel and earth surface monitoring data |
| CN112762853A (en) * | 2020-12-28 | 2021-05-07 | 中国科学院武汉岩土力学研究所 | Method and equipment for monitoring full deformation of duct piece in tunnel shield process |
| CN112762853B (en) * | 2020-12-28 | 2021-11-16 | 中国科学院武汉岩土力学研究所 | Method and equipment for monitoring full deformation of duct piece in tunnel shield process |
| CN113743440A (en) * | 2021-01-13 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Information processing method and device and storage medium |
| CN113240095A (en) * | 2021-06-07 | 2021-08-10 | 北京理工大学 | Casting cylinder cover mechanical property prediction method based on rough set and neural network |
| CN114254562A (en) * | 2021-12-20 | 2022-03-29 | 浙江大学 | Neural network-based shield tunnel segment floating prediction method |
| CN115217152A (en) * | 2022-07-29 | 2022-10-21 | 招商局重庆交通科研设计院有限公司 | Method and device for predicting opening and closing deformation of immersed tunnel pipe joint |
| CN117235874A (en) * | 2023-11-14 | 2023-12-15 | 中电建铁路建设投资集团有限公司 | Track deformation prediction method and system based on shield tunneling |
| CN117235874B (en) * | 2023-11-14 | 2024-02-20 | 中电建铁路建设投资集团有限公司 | Track deformation prediction method and system based on shield tunneling |
| CN117474170A (en) * | 2023-11-17 | 2024-01-30 | 中电建铁路建设投资集团有限公司 | Shield settlement deformation model construction method based on neural network |
| CN117474170B (en) * | 2023-11-17 | 2024-05-28 | 中电建铁路建设投资集团有限公司 | Shield settlement deformation model construction method based on neural network |
| CN117988867A (en) * | 2024-02-01 | 2024-05-07 | 中交隧道工程局有限公司 | Shield segment floating prediction method considering forming sequence influence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110442979B (en) | 2021-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110442979A (en) | The full Deformation Prediction method and system in the shield-tunneling construction tunnel based on BP neural network | |
| CN107480341A (en) | A kind of dam safety comprehensive method based on deep learning | |
| CN110992113A (en) | Neural network intelligent algorithm-based project cost prediction method for capital construction transformer substation | |
| CN109635461A (en) | A kind of application carrys out the method and system of automatic identification Grades of Surrounding Rock with brill parameter | |
| CN101788403B (en) | Progressive method for identifying loose support cable based on strain monitoring during support settlement | |
| CN110889588A (en) | Method for evaluating risk level of shield tunnel construction adjacent building by using factor judgment matrix | |
| CN109885907A (en) | A kind of Satellite Attitude Control System health state evaluation and prediction technique based on cloud model | |
| CN109034582A (en) | Tunnel Passing inrush through faults based on cloud model and combination weighting are dashed forward mud risk evaluating method | |
| CN112100727B (en) | Early warning prevention and control method for water burst of water-rich tunnel under influence of fault fracture zone | |
| CN110472363B (en) | Surrounding rock deformation grade prediction method and system suitable for high-speed railway tunnel | |
| Razavi Toosi et al. | Prioritizing watersheds using a novel hybrid decision model based on fuzzy DEMATEL, fuzzy ANP and fuzzy VIKOR | |
| CN106202731A (en) | Bridge crane multi-flexibl e dynamics structural optimization method | |
| CN110489844B (en) | Prediction method suitable for uneven large deformation grade of soft rock tunnel | |
| CN105718658A (en) | Large-size bridge online evaluating system | |
| CN108204944A (en) | The Buried Pipeline rate prediction method of LSSVM based on APSO optimizations | |
| CN110378574A (en) | Submerged tunnel Pressure Shield Tunnel face stability evaluation method, system and equipment | |
| CN106909999A (en) | The small-sized retired integrated evaluating method of earth and rockfill dam | |
| CN110889587B (en) | Power distribution network line risk assessment method | |
| CN116562331B (en) | Method for optimizing SVM by improving reptile search algorithm and application thereof | |
| Adoko et al. | Fuzzy inference system-based for TBM field penetration index estimation in rock mass | |
| CN112508679A (en) | Small and micro enterprise loan risk assessment method and device and storage medium | |
| Yao et al. | Hybrid model for displacement prediction of tunnel surrounding rock | |
| CN115526108A (en) | Intelligent dynamic landslide stability prediction method based on multi-source monitoring data | |
| Liu et al. | Condition evaluation for existing reinforced concrete bridge superstructure using fuzzy clustering improved by particle swarm optimisation | |
| Houria et al. | Maintenance strategy selection for medical equipments using fuzzy multiple criteria decision making approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |